Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior
Direct reconstruction methods have been developed to estimate parametric images directly from the measured PET sinograms by combining the PET imaging model and tracer kinetics in an integrated framework. Due to limited counts received, signal-to-noise-ratio (SNR) and resolution of parametric images produced by direct reconstruction frameworks are still limited. Recently supervised deep learning methods have been successfully applied to medical imaging denoising/reconstruction when large number of high-quality training labels are available. For static PET imaging, high-quality training labels can be acquired by extending the scanning time. However, this is not feasible for dynamic PET imaging, where the scanning time is already long enough. In this work, we proposed an unsupervised deep learning framework for direct parametric reconstruction from dynamic PET, which was tested on the Patlak model and the relative equilibrium Logan model. The training objective function was based on the PET statistical model. The patient's anatomical prior image, which is readily available from PET/CT or PET/MR scans, was supplied as the network input to provide a manifold constraint, and also utilized to construct a kernel layer to perform non-local feature denoising. The linear kinetic model was embedded in the network structure as a 1 ×1 ×1 convolution layer. Evaluations based on dynamic datasets of 18F-FDG and 11C-PiB tracers show that the proposed framework can outperform the traditional and the kernel method-based direct reconstruction methods.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:41 |
---|---|
Enthalten in: |
IEEE transactions on medical imaging - 41(2022), 3 vom: 01. März, Seite 680-689 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Gong, Kuang [VerfasserIn] |
---|
Links: |
---|
Themen: |
0Z5B2CJX4D |
---|
Anmerkungen: |
Date Completed 07.04.2022 Date Revised 03.03.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1109/TMI.2021.3120913 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM331934663 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM331934663 | ||
003 | DE-627 | ||
005 | 20231225214551.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/TMI.2021.3120913 |2 doi | |
028 | 5 | 2 | |a pubmed24n1106.xml |
035 | |a (DE-627)NLM331934663 | ||
035 | |a (NLM)34652998 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Gong, Kuang |e verfasserin |4 aut | |
245 | 1 | 0 | |a Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 07.04.2022 | ||
500 | |a Date Revised 03.03.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Direct reconstruction methods have been developed to estimate parametric images directly from the measured PET sinograms by combining the PET imaging model and tracer kinetics in an integrated framework. Due to limited counts received, signal-to-noise-ratio (SNR) and resolution of parametric images produced by direct reconstruction frameworks are still limited. Recently supervised deep learning methods have been successfully applied to medical imaging denoising/reconstruction when large number of high-quality training labels are available. For static PET imaging, high-quality training labels can be acquired by extending the scanning time. However, this is not feasible for dynamic PET imaging, where the scanning time is already long enough. In this work, we proposed an unsupervised deep learning framework for direct parametric reconstruction from dynamic PET, which was tested on the Patlak model and the relative equilibrium Logan model. The training objective function was based on the PET statistical model. The patient's anatomical prior image, which is readily available from PET/CT or PET/MR scans, was supplied as the network input to provide a manifold constraint, and also utilized to construct a kernel layer to perform non-local feature denoising. The linear kinetic model was embedded in the network structure as a 1 ×1 ×1 convolution layer. Evaluations based on dynamic datasets of 18F-FDG and 11C-PiB tracers show that the proposed framework can outperform the traditional and the kernel method-based direct reconstruction methods | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, N.I.H., Extramural | |
650 | 7 | |a Fluorodeoxyglucose F18 |2 NLM | |
650 | 7 | |a 0Z5B2CJX4D |2 NLM | |
700 | 1 | |a Catana, Ciprian |e verfasserin |4 aut | |
700 | 1 | |a Qi, Jinyi |e verfasserin |4 aut | |
700 | 1 | |a Li, Quanzheng |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE transactions on medical imaging |d 1982 |g 41(2022), 3 vom: 01. März, Seite 680-689 |w (DE-627)NLM082855269 |x 1558-254X |7 nnns |
773 | 1 | 8 | |g volume:41 |g year:2022 |g number:3 |g day:01 |g month:03 |g pages:680-689 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/TMI.2021.3120913 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 41 |j 2022 |e 3 |b 01 |c 03 |h 680-689 |